Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    common first names or surnames

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Ô
    -0.87
     Taiwan
    -0.74
    SourceFile
    -0.63
    ught
    -0.62
    enegger
    -0.62
    ãĥ¼ãĥ³
    -0.61
    dylib
    -0.61
    rency
    -0.60
    ociate
    -0.60
     overd
    -0.59
    POSITIVE LOGITS
    illard
    0.72
    aic
    0.70
    vic
    0.68
    atican
    0.67
    rama
    0.67
    tle
    0.66
    arella
    0.66
    henko
    0.66
    oshenko
    0.65
    ciating
    0.65
    Act Density 0.142%

    No Known Activations